{"id":"https://openalex.org/W2004459722","doi":"https://doi.org/10.1145/1076034.1076093","title":"Web-based acquisition of Japanese katakana variants","display_name":"Web-based acquisition of Japanese katakana variants","publication_year":2005,"publication_date":"2005-08-15","ids":{"openalex":"https://openalex.org/W2004459722","doi":"https://doi.org/10.1145/1076034.1076093","mag":"2004459722"},"language":"en","primary_location":{"id":"doi:10.1145/1076034.1076093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108515392","display_name":"Takeshi Masuyama","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Masuyama","raw_affiliation_strings":["University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020912760","display_name":"Hiroshi Nakagawa","orcid":"https://orcid.org/0000-0002-3024-9136"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Nakagawa","raw_affiliation_strings":["University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.10511183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"35","issue":null,"first_page":"338","last_page":"344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8308491706848145},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.7236557006835938},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7041885256767273},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.6916139125823975},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5911980867385864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5756485462188721},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5611424446105957},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4147738218307495},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38407641649246216},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37890225648880005},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2603026032447815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308491706848145},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.7236557006835938},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7041885256767273},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6916139125823975},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5911980867385864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5756485462188721},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5611424446105957},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4147738218307495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38407641649246216},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37890225648880005},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2603026032447815},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1076034.1076093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2010392031","https://openalex.org/W2011806618","https://openalex.org/W2032571942","https://openalex.org/W2060165117","https://openalex.org/W2097734711","https://openalex.org/W2404904334"],"related_works":["https://openalex.org/W3153459181","https://openalex.org/W2147866274","https://openalex.org/W2350015575","https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W2371976984","https://openalex.org/W1555832326","https://openalex.org/W2352160949","https://openalex.org/W4298186509","https://openalex.org/W2556702969"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,11],"method":[4,106,142],"of":[5,39,71,99,113,140,153,177,192,201,203],"detecting":[6],"Japanese":[7,204],"Katakana":[8,14,48,164,194],"variants":[9,65],"from":[10,171,197],"large":[12],"corpus.":[13],"words,":[15],"which":[16],"are":[17],"mainly":[18],"used":[19],"as":[20,52,129,131],"loanwords,":[21],"cause":[22],"problems":[23],"with":[24,60,95,133,162],"information":[25],"retrieval":[26],"and":[27,37,55,66,101,156,173,186],"so":[28],"on,":[29],"because":[30],"transliteration":[31],"creates":[32],"several":[33],"variations":[34],"in":[35,108,148,189],"spelling":[36],"all":[38],"these":[40,82,85],"can":[41],"be":[42],"orthographic.":[43],"Previous":[44],"works":[45],"manually":[46,134],"defined":[47,68],"rewrite":[49],"rules":[50],"such":[51],"%Y":[53],"(be)":[54],"%t%'":[56],"(ve)":[57],"being":[58],"replaceable":[59],"each":[61,72,114,154],"other,":[62],"for":[63],"generating":[64],"also":[67,182],"the":[69,96,111,138,190],"weight":[70,112,152],"operation":[73,116],"to":[74,80,92,150,159],"edit":[75,115,178],"one":[76,132],"string":[77],"into":[78],"another":[79],"detect":[81],"variants.":[83,103],"However,":[84],"previous":[86],"researches":[87],"have":[88],"not":[89],"been":[90],"able":[91,158],"keep":[93,160],"up":[94,161],"ever-increasing":[97],"number":[98],"loanwords":[100,165],"their":[102],"With":[104],"our":[105,141],"proposed":[107],"this":[109],"paper,":[110],"is":[117],"mechanically":[118],"assigned":[119],"based":[120],"on":[121],"Web":[122,172],"data.":[123],"In":[124],"experiments,":[125],"it":[126],"performed":[127],"almost":[128],"well":[130],"determined":[135],"weights.":[136],"Thus,":[137],"advantages":[139],"are:":[143],"1)":[144],"need":[145],"no":[146],"expertise":[147],"linguistics":[149],"determine":[151],"operation,":[155],"2)":[157],"new":[163,175],"only":[166],"by":[167],"collecting":[168],"text":[169],"data":[170],"acquiring":[174],"weights":[176],"operations":[179],"automatically.":[180],"It":[181],"achieved":[183],"98.6%":[184],"recall":[185],"86.3%":[187],"precision":[188],"task":[191],"extracting":[193],"variant":[195],"pairs":[196],"38":[198],"year's":[199],"worth":[200],"corpora":[202],"newspaper":[205],"articles.":[206]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}